Landseer offers a containerized modular system to integrate and evaluate combinations of machine learning defenses, with an initial analysis of 35 defenses highlighting replicability challenges.
Jaakkola
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Most recent work on interpretability of complex machine learning models has focused on estimating $\textit{a posteriori}$ explanations for previously trained models around specific predictions. $\textit{Self-explaining}$ models where interpretability plays a key role already during learning have received much less attention. We propose three desiderata for explanations in general -- explicitness, faithfulness, and stability -- and show that existing methods do not satisfy them. In response, we design self-explaining models in stages, progressively generalizing linear classifiers to complex yet architecturally explicit models. Faithfulness and stability are enforced via regularization specifically tailored to such models. Experimental results across various benchmark datasets show that our framework offers a promising direction for reconciling model complexity and interpretability.
years
2026 3verdicts
UNVERDICTED 3representative citing papers
DINO-QPM adapts frozen DINOv2 models via average-pooled patch embeddings and a sparsity loss to deliver both higher classification accuracy and human-interpretable global explanations.
Benchmark of local explainability methods on tabular data finds explanation quality driven primarily by dataset complexity rather than model predictive performance.
citing papers explorer
-
DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification
DINO-QPM adapts frozen DINOv2 models via average-pooled patch embeddings and a sparsity loss to deliver both higher classification accuracy and human-interpretable global explanations.